Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: Multivariate GARCH

From   KREISER Swetlana <>
To   "" <>
Subject   st: Multivariate GARCH
Date   Thu, 25 Jul 2013 14:03:23 +0000

Dear all,

I would like to make an estimation of a multivariate GARCH model in Stata for my Master's thesis. In particular, it should be a BEKK (Engle and Kroner (1995)) specification. The mgarch command in Stata only supports diagonal VECH and conditional correlation models. Is there any other possibility, that I am not aware of, how to estimate the BEKK MGARCH in Stata?

Besides, when using the VCC approach instead, the predict command in Stata will give the residuals of the mean equation. According to the manual, the residual consists of et=(Ht^1/2)*vt (the conditional covariance matrix Ht and the iid disturbances vt). For my analysis, I require a time series of these disturbances, not the residuals. How could I get them in Stata?

I would appreciate any help!

Thank you very much!

Kind regards,


The University of Edinburgh is a charitable body, registered in
Scotland, with registration number SC005336.

*   For searches and help try:

© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index